No Cover Image

Conference Paper/Proceeding/Abstract 1434 views 250 downloads

Nested Shallow CNN-Cascade for Face Detection in the Wild

Jingjing Deng, Xianghua Xie Orcid Logo

2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition, Pages: 165 - 172

Swansea University Authors: Jingjing Deng, Xianghua Xie Orcid Logo

DOI (Published version): 10.1109/FG.2017.29

Abstract

We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is con...

Full description

Published in: 2017 IEEE 12th International Conference on Automatic Face & Gesture Recognition
ISBN: 978-1-5090-4024-7 978-1-5090-4023-0
Published: IEEE 2017
Online Access: http://csvision.swan.ac.uk/uploads/Site/Publication/jd17fg.pdf
URI: https://cronfa.swan.ac.uk/Record/cronfa32108
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract: We propose a nested CNN-cascade learning algorithm that adopts shallow neural network architectures that allow efficient and progressive elimination of negative hypothesis from easy to hard via self-learning discriminative representations from coarse to fine scales. The face detection problem is considered as solving three sub-problems: eliminating easy background with a simple but fast model, then localising the face region with a soft-cascade, followed by precise detection and localisation by verifying retained regions with a deeper and stronger model.
Keywords: Deep Learning, Neural Network, Face Detection, CNN
College: Faculty of Science and Engineering
Start Page: 165
End Page: 172